INDEX

Explanations

expressions of emotions and feelings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Stow

-0.93

Zeneca

-0.93

 Astor

-0.89

 Farmington

-0.84

ongyang

-0.83

 twain

-0.82

 MainAxisSize

-0.82

 corrom

-0.81

 Kirkwood

-0.81

 Tartar

-0.80

POSITIVE LOGITS

 felt

1.55

 feeling

1.48

Feels

1.43

 feels

1.41

Felt

1.39

 Felt

1.37

 Feels

1.37

 feel

1.35

Feel

1.33

 Feel

1.32

Activations Density 0.061%

expressions of emotions and feelings

No Comments

No Known Activations